Balestra predicts drug-target interactions. However the latent factor model that powers Balestra can also be used to query for drug-drug similarity. This is achieved by computing the distance between the latent variable (LV) vectors corresponding to different drugs. The LV similarity between two drugs represents the similarity between the target profiles of these two drugs. Therefore the drugs with similar target profiles have score high and vice versa.
Balestra can give the drugs that are most similar to a query. This is achieved by providing only one drug name. Alternatively, the user can query for the similarity between a drug-drug pair by simply providing the name of the second drug in the specified box.
Built by: Murat Can Cobanoglu.
- Bahar Lab at the
University of Pittsburgh School of Medicine,
Dept of Computational and Systems Biology
- University of Pittsburgh Drug Discovery Institute,
Funding: Support for BalestraWeb development is provided by NIH awards U19 AI068021 and P01 DK096990.
Copyright © 2013-2014, University of Pittsburgh